INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ereum

-0.26

 authDomain

-0.26

ios

-0.26

osaur

-0.26

 Reserve

-0.26

_reserve

-0.24

ë§Ī

-0.24

Ãłi

-0.24

åľī

-0.23

åĺĪ

-0.23

POSITIVE LOGITS

é¦Ī

0.28

INV

0.26

æĸ¥

0.25

æ¸©åº¦

0.25

é¾ĻéĹ¨

0.24

ç²īæľ«

0.24

çł´åĿı

0.24

ilion

0.23

æĵįä½ľ

0.23

INV

0.23

Activations Density 0.167%

No Known Activations

This feature has no known activations.